An international team of researchers, led by Professor Ge Jian of the Shanghai Astronomical Observatory, has utilized cutting-edge artificial intelligence to discover five new exoplanets. By developing a sophisticated deep learning algorithm that integrates Graphics Processing Unit (GPU) phase folding with neural networks, the team analyzed data from the Kepler space telescope's 2017 release.
These newly identified planets are ultra-short period exoplanets, each with an orbital period shorter than 24 hours and diameters smaller than Earth's. Remarkably, four of these celestial bodies are among the smallest exoplanets ever discovered, with dimensions comparable to Mars, and they orbit exceptionally close to their host stars.
This breakthrough marks the first time astronomers have employed AI for both the detection of candidate signals and the confirmation of genuine exoplanets. The findings represent a significant advancement in the use of AI in astronomical research and open new avenues for exploring distant worlds.
The study has been published in the esteemed journal Monthly Notices of the Royal Astronomical Society (MNRAS), highlighting the potential of AI to accelerate discoveries in the field of exoplanet exploration.
Reference(s):
cgtn.com
